Abstract
Organic anion transporting polypeptides (OATPs) are membrane transporters crucial for drug uptake and distribution in the human body. OATPs can mediate drug-drug interactions (DDIs) in which the interaction of one drug with an OATP impairs the uptake of another drug, resulting in potentially fatal pharmacological effects. Predicting OATP-mediated DDIs is challenging, due to limited information on OATP inhibition mechanisms and inconsistent experimental OATP inhibition data across different studies. This study introduces Heterogeneous OATP-Ligand Interaction Graph Neural Network (HOLIgraph), a novel computational model that integrates molecular modeling with a graph neural network to enhance the prediction of drug-induced OATP inhibition. By combining ligand (i.e., drug) molecular features with protein-ligand interaction data from rigorous docking simulations, HOLIgraph outperforms traditional DDI prediction models which rely solely on ligand molecular features. HOLIgraph achieved a median balanced accuracy of over 90 percent when predicting inhibitors for OATP1B1, significantly outperforming purely ligand-based models. Beyond improving inhibition prediction, the data used to train HOLIgraph can enable the characterization of protein residues involved in inhibitory drug-OATP interactions. We identified certain OATP1B1 residues that preferentially interact with inhibitors, including I46 and K49. We anticipate such interaction information will be valuable to future structural and mechanistic investigations of OATP1B1.
Scientific Contribution HOLIgraph introduces a new paradigm for DDI prediction by incorporating protein-ligand interactions derived from docking simulations into a graph neural net framework. This approach, enabled by recent structural breakthroughs for OATP1B1, represents a significant departure from traditional models that rely only on ligand features. By achieving high predictive accuracy and uncovering mechanistic insights, HOLIgraph sets a new trajectory for computational tools in drug design and DDI prediction.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
General reformatting; Title and entire manuscript and supplement updated with revised model name; abstract and main text revised for clarity to broader audience; Figures replace, revised, or reorganized for clarity to broader audience; Supplemental Information updated
List of abbreviations
- OATP:
- Organic anion transporting polypeptide
- DDI:
- Drug-drug interaction
- HOLIgraph:
- Heterogeneous OATP-Ligand Interaction Graph Neural Network
- FDA:
- Food and Drug Administration
- Cryo-EM:
- Cryogenic electron microscopy
- GNN:
- Graph neural network
- PLIP:
- Protein-Ligand Interaction Profiler
- ECFP:
- Extended-connectivity fingerprint
- PLIF:
- Protein-ligand interaction fingerprint
- XGBoost:
- Extreme gradient boosting
- hENT1:
- Human equilibrative nucleoside transporter 1
- HEK293:
- Human embryonic kidney 293
- AUC:
- Area under the curve